The Hacker News - New AI Jailbreak Method 'Bad Likert Judge' Boosts Attack Success Rates by Over 60%

Cybersecurity researchers have shed light on a new jailbreak technique that could be used to get past a large language model's (LLM) safety guardrails and produce potentially harmful or malicious responses. The multi-turn (aka many-shot) attack strategy has been codenamed Bad Likert Judge by Palo Alto Networks Unit 42 researchers Yongzhe Huang, Yang Ji, Wenjun Hu, Jay Chen, Akshata Rao, and

from The Hacker News https://thehackernews.com/2025/01/new-ai-jailbreak-method-bad-likert.html

Comments

Popular posts from this blog

Krebs - NY Charges First American Financial for Massive Data Leak

KnowBe4 - Scam Of The Week: "When Users Add Their Names to a Wall of Shame"

Krebs - U.S. Army Soldier Arrested in AT&T, Verizon Extortions